Natural Language Processing with PyTorch

This is a paid AI training workshop. You can join anywhere with zoom. Please register and attend here: https://learn.xnextcon.com/course/coursedetails/C2020121210

Cost $125. Use promote code ACMSFBAY20 for a $20 discount as SFBay ACM members. You may join us on http://www.sfbayacm.org/join-us/ as well.

Abstract:
Natural Language Processing (NLP) is the fastest-growing field of deep learning with interest and funding from top AI companies to solve problems of language, text, and unstructured information. This has resulted in a tremendous focus on model building that combines language, mathematics, and computer science.
This workshop will focus on problems of text summarization, question answering, and sentiment classification using modern approaches to model-building (GNMT, BERT, and GPT2). We will apply this to real-world problems to create an NLP pipeline on top of the PyTorch framework and spaCy.

Learning Outcomes: At the end of this workshop, you will have a working knowledge of the PyTorch API to train your own deep learning models. You will be able to use OpenVINO to run model optimizer to use less compute and memory for deploying model inference in production.

Session Outline
Day 1:

1. Module 1 (20mins, Lecture): Foundations
   a. Fundamentals and application of Language Modeling Tools
   b. Classical vs DL NLP
   c. NLP Pipeline
2. Lab (20mins): NLTK from scratch
   . Setting up your environment

a. NLTK (tokenization)
3. Module 2 (30mins):
. Use NLP pipeline to process documents
a. POS, Word embedding
4. Lab (30mins)
Break (15mins)
5. Module 3 Lecture (30mins): Key packages & libraries in NLP; dive into SpaCy
6. Lab (20mins): SpaCy
7. Module 4 Lecture (30mins): TFIDF & Logistic Regression
8. Lab (30mins): Disaster Detection using TFIDF and Logistic Regression
Day 2:
9. Recap
10. Lab (30mins): Quora, using LSTM
11. Module 5 Lecture: Introduction to pre-trained models such as BERT
12. Lab (20mins): Disaster Detection using BERT
13. Module 6: Sentiment analysis
14. Lab (20mins): Headline Classifier using BERT
15. Lab (20mins): LSTM based sequence classifier
16. Module 7: Text summarization
17. Lab (20mins): Text summarization
18. Module 8: NLP in production
a. Scheduler Overview
b. Implementation for AirFlow

Background knowledge
Python coding skills, intro to PyTorch framework is helpful, familiarity with NLP

Visit https://www.meetup.com/SF-Bay-ACM/events/270972953/
for more content introduction. We made this course easier for both students and instructors by join efforts with AICamp, and more effective learning on each session.

COURSE SCHEDULE:
Session 1: Dec 12, 10am-11:30am PST (US Pacific Time, GTM-8)
Session 2: Dec 12, 11:30am-1:00pm PST
Session 3: Dec 13, 10am-11:30am PST
Session 4: Dec 13, 11:30am-1:00pm PST

COURSE INCLUDE:
4 sessions / 6 hours
Live session (with zoom) and real time interaction
Slack support during/after class

Instructor Bio
Ravi Ilango
Sr. Data Scientist working on a variety of revenue-generating projects for clients involving machine learning and deep learning. He worked as Sr Data Scientist at Apple for 10 years, and a Sr Program Manager at Applied Materials

Yashesh Shroff,PhD
Lead AI of Intel, where he focuses on enabling the AI ecosystem on heterogeneous compute. He has over 15 years of technical and enabling experience, spanning optical modeling, statistical analysis, and capital equipment supply chain at Intel. He has over 20 published papers and 4 patents. He has a Ph.D. in EECS from UC Berkeley